English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper focuses on the problem of online golf ball detection and trackingfrom image sequences. An efficient real-time approach is proposed by exploitingconvolutional neural networks (CNN) based object detection and a Kalman filterbased prediction. Five classical deep learning-based object detection networksare implemented and evaluated for ball detection, including YOLO v3 and itstiny version, YOLO v4, Faster R-CNN, SSD, and RefineDet. The detection isperformed on small image patches instead of the entire image to increase theperformance of small ball detection. At the tracking stage, a discrete Kalmanfilter is employed to predict the location of the ball and a small image patchis cropped based on the prediction. Then, the object detector is utilized torefine the location of the ball and update the parameters of Kalman filter. Inorder to train the detection models and test the tracking algorithm, acollection of golf ball dataset is created and annotated. Extensive comparativeexperiments are performed to demonstrate the effectiveness and superiortracking performance of the proposed scheme.

Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter